© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 64254
    Prev
    Next
    INDEX
    Explanations

    computing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ben
    -0.26
    ServletRequest
    -0.26
     voluntarily
    -0.26
    bens
    -0.25
    osterone
    -0.25
     Spar
    -0.24
    ful
    -0.24
    aday
    -0.24
    akest
    -0.24
    room
    -0.23
    POSITIVE LOGITS
    èīº
    0.30
    åı¯æĥ³èĢĮçŁ¥
    0.25
    å«Į
    0.25
    çŃ¾ç½²
    0.24
    isers
    0.24
    骰
    0.24
     Heller
    0.23
    ï¼Ħ
    0.23
    åī¯
    0.23
    éĺŁåijĺ们
    0.23
    Activations Density 11.027%

    No Known Activations